{"total":22,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2509.15279","title":"Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning","created":"2025-09-18","cited_by_count":10,"area":"lr"},{"id":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","cited_by_count":10,"area":"lr"},{"id":"2603.03292","title":"From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG","created":"2026-02-06","cited_by_count":7,"area":"lr"},{"id":"2604.08203","title":"MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning","created":"2026-04-09","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2604.08559","title":"Medical Reasoning with Large Language Models: A Survey and MR-Bench","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2602.01779","title":"LingLanMiDian: Systematic Evaluation of LLMs on TCM Knowledge and Clinical Reasoning","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.03340","title":"MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2604.23605","title":"Thinking Like a Clinician: A Cognitive AI Agent for Clinical Diagnosis via Panoramic Profiling and Adversarial Debate","created":"2026-04-26","cited_by_count":1,"area":"lr"},{"id":"2509.21266","title":"Rethinking Explainable Disease Prediction: Synergizing Accuracy and Reliability via Reflective Cognitive Architecture","created":"2025-09-25","cited_by_count":0,"area":"lr"},{"id":"2601.13690","title":"Dr. Assistant: Enhancing Clinical Diagnostic Inquiry via Structured Diagnostic Reasoning Data and Reinforcement Learning","created":"2026-01-20","cited_by_count":0,"area":"lr"},{"id":"2605.27860","title":"C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.08875","title":"Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2606.11675","title":"Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.24510","title":"A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial","created":"2026-06-23","cited_by_count":0,"area":"lr"},{"id":"2607.02983","title":"Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2608.03028","title":"Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.22622","title":"Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains","created":"2026-08-23","cited_by_count":0,"area":"lr"},{"id":"2608.26147","title":"CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2609.24480","title":"Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2610.14705","title":"Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine","created":"2026-10-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}